Papers by Emiel Krahmer
Aspect-based summarization of pros and cons in unstructured product reviews (C18-1)
Copied to clipboard
| Challenge: | SynPat, a system based on syntactic phrases selected on the basis of valence scores, and a neural-network-based system trained on clusters of word-embedding encodings of similar pros and cons are compared to SynPat. |
| Approach: | They propose to use syntactic phrases selected on the basis of valence scores to generate pros and cons summaries. |
| Outcome: | The proposed systems outperform the baseline systems on held-out reviews with gold-standard pros and cons and on human annotators on relevance and completeness. |
DIDEC: The Dutch Image Description and Eye-tracking Corpus (C18-1)
Copied to clipboard
| Challenge: | Using a corpus of spoken Dutch image descriptions and eye-tracking data, we can gain a deeper understanding of the image description task, especially how visual attention is correlated with the image descriptions. |
| Approach: | They present a corpus of spoken Dutch image descriptions paired with eye-tracking data from Free viewing and Description viewing tasks to provide an initial analysis of self-corrections in image descriptions. |
| Outcome: | The results show that the eye-tracking data for the description viewing task is more coherent than for the free-viewing task, and that variation in image descriptions is only moderately correlated across different languages. |
Automatic identification of writers’ intentions: Comparing different methods for predicting relationship goals in online dating profile texts (D19-55)
Copied to clipboard
| Challenge: | lexicon-based text analysis methods such as LIWC have been criticized by computational linguists for their lack of adaptability, but they have not been systematically compared with either human evaluations or machine learning approaches. |
| Approach: | They used a corpus of online dating profile texts to compare LIWC, machine learning, and a human baseline to assess their effectiveness on a relationship goal classification task. |
| Outcome: | The proposed methods were compared with a corpus of online dating profile texts and a human baseline. |
Preregistering NLP research (2021.naacl-main)
Copied to clipboard
| Challenge: | Preregistration refers to specifying what you are going to do, and what you expect to find in your study, before carrying out the study. |
| Approach: | They propose to use preregistration to specify what you are going to do and what you expect to find in your study, and propose several preregistrations questions for different kinds of studies. |
| Outcome: | The proposed preregistration form could provide firmer grounds for slow science in NLP research. |
How Well Can Large Language Models Reflect? A Human Evaluation of LLM-generated Reflections for Motivational Interviewing Dialogues (2025.coling-main)
Copied to clipboard
Erkan Basar, Xin Sun, Iris Hendrickx, Jan de Wit, Tibor Bosse, Gert-Jan De Bruijn, Jos A. Bosch, Emiel Krahmer
| Challenge: | Motivational Interviewing (MI) is a counseling technique that promotes behavioral change through reflective responses to mirror or refine client statements. |
| Approach: | They assess the potential of Large Language Models (LLMs) to generate MI reflections via three LLMs: GPT-4, Llama-2, and BLOOM. |
| Outcome: | The proposed models generate meaningful reflections comparable to human therapists, but significant challenges remain. |
Surface Realization Shared Task 2019 (MSR19): The Team 6 Approach (D19-63)
Copied to clipboard
| Challenge: | This paper describes the approach developed by the Tilburg University team for the shallow track of the Multilingual Surface Realization Shared Task 2019 (SR'19). |
| Approach: | They propose a method for the shallow track of the Multilingual Surface Realization Shared Task 2019 using a rule-based and a statistical machine translation (SMT) model. |
| Outcome: | The proposed approach can generate texts in 11 languages, compared with the submission of the same approach for the same task in 2018 which only covered 6 languages. |
Evaluating the text quality, human likeness and tailoring component of PASS: A Dutch data-to-text system for soccer (C18-1)
Copied to clipboard
| Challenge: | PASS is a data-to-text system that generates Dutch soccer reports from match statistics which are automatically tailored towards fans of one club or the other. |
| Approach: | They propose to evaluate PASS, a data-to-text system that generates Dutch soccer reports from match statistics which are automatically tailored towards fans of one club or the other. |
| Outcome: | The proposed system generates Dutch soccer reports automatically tailored to fans of one club or the other. |
Neural data-to-text generation: A comparison between pipeline and end-to-end architectures (D19-1)
Copied to clipboard
| Challenge: | Traditionally, data-to-text applications have been designed using a modular pipeline architecture, in which the non-linguistic input data is converted into natural language through several intermediate transformations. |
| Approach: | They propose to use Gated-Recurrent Units and Transformer to implement neural pipelines for data-to-text generation. |
| Outcome: | The proposed models generalize better to unseen inputs and have better performance than the existing pipeline architectures. |
Eliciting Motivational Interviewing Skill Codes in Psychotherapy with LLMs: A Bilingual Dataset and Analytical Study (2024.lrec-main)
Copied to clipboard
Xin Sun, Jiahuan Pei, Jan de Wit, Mohammad Aliannejadi, Emiel Krahmer, Jos T.P. Dobber, Jos A. Bosch
| Challenge: | Motivational interviewing (MI) is an essential, directive, client-centered counseling technique. |
| Approach: | They propose a bilingual dataset of MI conversations in English and Dutch . they propose an approach to elicit MISC expertise from Large language models . |
| Outcome: | The proposed approach yields results aligned with expert annotations and maintains consistent performance across languages. |
NeuralREG: An end-to-end approach to referring expression generation (P18-1)
Copied to clipboard
| Challenge: | Referring Expression Generation models typically rely on features such as salience and grammatical function to make decisions about form and content. |
| Approach: | They propose a new approach that makes decisions about form and content in one go . they use a delexicalized version of the WebNLG corpus to test the approach . |
| Outcome: | The proposed approach significantly improves over two strong baselines. |